Due to the large size and lack of fine-grained annotation, Whole Slide Images (WSIs) analysis is commonly approached as a Multiple Instance Learning (MIL) problem. However, previous studies only learn from training data, posing a stark contrast to how human clinicians teach each other and reason about histopathologic entities and factors. Here, we present a novel knowledge concept-based MIL framework, named ConcepPath, to fill this gap. Specifically, ConcepPath utilizes GPT-4 to induce reliable disease-specific human expert concepts from medical literature and incorporate them with a group of purely learnable concepts to extract complementary knowledge from training data. In ConcepPath, WSIs are aligned to these linguistic knowledge concepts by utilizing the pathology vision-language model as the basic building component. In the application of lung cancer subtyping, breast cancer HER2 scoring, and gastric cancer immunotherapy-sensitive subtyping tasks, ConcepPath significantly outperformed previous SOTA methods, which lacked the guidance of human expert knowledge.
Denosumab, a RANK ligand inhibitor, is primarily used to prevent osteoclastogenesis in the treatment of conditions such as osteoporosis, bone metastasis, and giant cell tumor of bone (GCTB). RANK ligand also plays an important role in immunity by activating NF-κB and its target genes, including the osteopontin-coding gene SPP1 (also known as OPN), which is linked to CXCL9:SPP1 macrophage polarization and prognosis. In this study, we explored an additional role of denosumab in enhancing antitumor immunity in patients. Single-cell RNA sequencing was performed on nine human GCTB samples, including six untreated and three treated only with denosumab, to exclude confounding treatment factors linked with bone metastasis samples. We further analyzed paired samples collected before and after denosumab treatment from a cohort of nine patients with GCTB and conducted a pan-cancer analysis of 34 distinct types of cancers. Our single-cell analysis of GCTB resulted in a comprehensive cell atlas revealing an antitumor role of denosumab in inhibiting SPP1 expression and augmenting active cytotoxic T-cell abundance. Furthermore, we validated this immunomodulatory role of denosumab using the paired GCTB samples. Finally, the pan-cancer analysis supported a negative correlation between SPP1 and CD8A levels, with the CD8A:SPP1 ratio correlating with overall survival in 14 cancer types, which was superior to either CD8A or SPP1 alone. Our research provides clinical evidence that denosumab improves antitumor immunity by decreasing SPP1 expression and enhancing cytotoxic T-cell activity, serving as a milestone in the development of innovative use of denosumab and offering potential benefits to patients with elevated levels of SPP1.
Deep myxoid soft tissue lesions have posed a diagnostic challenge for pathologists due to significant histological overlap and regional heterogeneity, especially when dealing with small biopsies which have profoundly low accuracy. However, accurate diagnosis is important owing to difference in biological behaviors and response to adjuvant therapy, that will guide the extent of surgery and the need for neo-adjuvant therapy. Herein, we trained two convolutional neural network models based on a total of 149,130 images representing diagnoses of extra skeletal myxoid chondrosarcoma, intramuscular myxoma, low-grade fibromyxoid sarcoma, myxofibrosarcoma and myxoid liposarcoma. Both AI models outperformed all the pathologists, with a significant improvement of accuracy up to 97% compared to average pathologists of 69.7% (p < 0.00001), corresponding to 90% reduction in error rate. The area under curve of the best AI model was on average 0.9976. It could assist pathologists in clinical practice for accurate diagnosis of deep soft tissue myxoid lesions, and guide clinicians for precise and optimal treatment for patients.
Image‐based cytometry faces challenges due to technical variations arising from different experimental batches and conditions, such as differences in instrument configurations or image acquisition protocols, impeding genuine biological interpretation of cell morphology. Existing solutions, often necessitating extensive pre‐existing data knowledge or control samples across batches, have proved limited, especially with complex cell image data. To overcome this, “Cyto‐Morphology Adversarial Distillation” (CytoMAD), a self‐supervised multi‐task learning strategy that distills biologically relevant cellular morphological information from batch variations, is introduced to enable integrated analysis across multiple data batches without complex data assumptions or extensive manual annotation. Unique to CytoMAD is its “morphology distillation”, symbiotically paired with deep‐learning image‐contrast translation—offering additional interpretable insights into label‐free cell morphology. The versatile efficacy of CytoMAD is demonstrated in augmenting the power of biophysical imaging cytometry. It allows integrated label‐free classification of human lung cancer cell types and accurately recapitulates their progressive drug responses, even when trained without the drug concentration information. CytoMAD also allows joint analysis of tumor biophysical cellular heterogeneity, linked to epithelial‐mesenchymal plasticity, that standard fluorescence markers overlook. CytoMAD can substantiate the wide adoption of biophysical cytometry for cost‐effective diagnosis and screening.